MODEL ID runware:ace-step@v1.5-base

live

ACE-Step v1.5 Base

January 1, 2026

ACE-Step v1.5 Base is an open-source music generation foundation model built on a hybrid LLM planner and Diffusion Transformer architecture. It generates full tracks from text prompts with support for voice cloning, lyric editing, remixing, cover generation, and compositions up to 10 minutes. It supports over 50 languages and runs on consumer hardware with under 4GB VRAM.

API Options

Platform-level options for task execution and delivery.

taskType string required value: audioInference: Identifier for the type of task being performed

taskUUID string required UUID v4: UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

outputType string default: URL: Audio output type.

Allowed values 3 values

outputFormat string default: MP3

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

`MP3`: Compressed audio, smaller file size.
`WAV`: Uncompressed, high-quality audio.
`FLAC`: Lossless compression.
`OGG`: Open-source compressed audio format (Vorbis codec).

Allowed values 4 values

audioSettings object

Audio encoding settings for controlling the bitrate, number of channels, and sample rate of the generated audio. Only applicable for lossy output formats (MP3 and OGG). When using lossless formats (WAV or FLAC), this parameter must not be provided.

The available sample rates and valid bitrate ranges depend on the output format. For OGG, bitrate limits also vary by the number of channels.

MP3 bitrate limits

Bitrate limits for MP3 are the same regardless of mono or stereo.

Sample Rate	Min Bitrate	Max Bitrate
8,000 Hz	8 kbps	64 kbps
11,025 Hz	8 kbps	64 kbps
12,000 Hz	8 kbps	64 kbps
16,000 Hz	8 kbps	160 kbps
22,050 Hz	8 kbps	160 kbps
24,000 Hz	8 kbps	160 kbps
32,000 Hz	32 kbps	320 kbps
44,100 Hz	32 kbps	320 kbps
48,000 Hz	32 kbps	320 kbps

OGG bitrate limits — Mono (1 channel)

Sample Rate	Min Bitrate	Max Bitrate
8,000 Hz	8 kbps	40 kbps
12,000 Hz	16 kbps	48 kbps
16,000 Hz	16 kbps	96 kbps
24,000 Hz	16 kbps	80 kbps
48,000 Hz	32 kbps	224 kbps

OGG bitrate limits — Stereo (2 channels)

Sample Rate	Min Bitrate	Max Bitrate
8,000 Hz	16 kbps	80 kbps
12,000 Hz	16 kbps	96 kbps
16,000 Hz	24 kbps	192 kbps
24,000 Hz	32 kbps	160 kbps
48,000 Hz	48 kbps	256 kbps

Lossless formats: When outputFormat is set to WAV or FLAC, the audioSettings parameter is not available since these formats produce uncompressed or lossless audio with no configurable encoding settings.

Properties 3 properties

audioSettings » bitrate bitrate integer min: 8: Audio bitrate in kbps.

audioSettings » channels channels integer default: 2: Number of audio channels. 1 for mono, 2 for stereo.

Allowed values 2 values

audioSettings » sampleRate sampleRate integer: Audio sample rate in Hz.

webhookURL string URI

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

Learn more 1 resource

Webhooks
PLATFORM

deliveryMethod string default: sync

Determines how the API delivers task results.

Allowed values 2 values

: Returns complete results directly in the API response.
: Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

Learn more 1 resource

Task Polling
PLATFORM

uploadEndpoint string URI

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

Common use cases:

Cloud storage: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
CDN integration: Upload to content delivery networks for immediate distribution.

// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg

The content data will be sent as the request body to the specified URL when generation is complete.

ttl integer min: 60: Time-to-live (TTL) in seconds for generated content. Only applies when outputType is URL.

includeCost boolean default: false: Include task cost in the response.

numberResults integer min: 1 max: 4 default: 1: Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

Inputs

Input resources for the task (images, audio, etc). These must be nested inside the inputs object.

inputs » audio audio string: Audio input (UUID or URL).

Generation Parameters

Core parameters for controlling the generated content.

model string required value: runware:ace-step@v1.5-base

Identifier of the model to use for generation.

Learn more 3 resources

positivePrompt string required min: 2 max: 3000

Text prompt describing elements to include in the generated output.

Learn more 2 resources

negativePrompt string min: 2 max: 3000

Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).

Learn more 1 resource

Text To Image: Prompts Guiding The Generation
GUIDE

duration float min: 6 max: 300 step: 0.1 default: 60: Length of the generated audio track in seconds.

seed integer min: 0 max: 2147483647: Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

steps integer min: 1 max: 300 default: 100

Total number of denoising steps. Higher values generally produce more detailed results but take longer.

Learn more 1 resource

Text To Image: Steps Trading Quality For Speed
GUIDE

CFGScale float min: 1 max: 30 step: 0.01 default: 10

Guidance scale. Higher values follow the prompt more closely at the cost of quality.

Learn more 1 resource

Text To Image: Cfg Scale Balancing Creativity And Control
GUIDE

strength float min: 0 max: 1 step: 0.01 default: 0.5

Fraction of steps using the input source instead of generated output.

Learn more 3 resources

Settings

Technical parameters to fine-tune the inference process. These must be nested inside the settings object.

settings » bpm bpm integer min: 30 max: 300: Beats per minute. If not set, the model decides automatically.

settings » coverConditioningScale coverConditioningScale float min: 0 max: 1 step: 0.01 default: 1: Fraction of steps using source-audio conditioning.

settings » guidanceType guidanceType string default: apg

Controls how guidance is applied during generation.

Allowed values 2 values

: Adaptive Projected Guidance.
: Classifier-Free Guidance.

settings » keyScale keyScale string: Musical key and scale in '{Note}{Accidental} {Mode}' format (e.g. 'C major', 'F# minor', 'Bb major').

settings » lyrics lyrics string min: 10 max: 3000 default:: Song lyrics, typically formatted like a lyrics website.

settings » repaintingEnd repaintingEnd float min: 0 max: 300: End time in seconds for repaint region. Requires input audio. Values beyond audio duration append new audio.

settings » repaintingStart repaintingStart float min: -300 max: 300: Start time in seconds for repaint region. Requires input audio. Negative values prepend audio before the start.

settings » timeSignature timeSignature string: Beats per measure. Empty string lets the model decide.

Allowed values 4 values

settings » vocalLanguage vocalLanguage string default: en: ISO 639-1 language code for vocals. unknown for instrumental or auto detection.

Allowed values 51 values

taskType string required value: audioInference: Type of the task.

taskUUID string required UUID v4: UUID of the task.

audioUUID string required UUID v4: UUID of the output audio.

audioURL string URI: URL of the output audio.

audioBase64Data string: Base64-encoded audio data.

audioDataURI string URI: Data URI of the output audio.

seed integer: The seed used for generation. If none was provided, shows the randomly generated seed.

cost float: Task cost in USD. Present when includeCost is set to true in the request.

Text to Audio

Midnight Roller Rink Synthwave

0:00

Request

{
  "taskType": "audioInference",
  "taskUUID": "db9ad4da-7608-4fe2-9111-a9b0e6bc94a7",
  "model": "runware:ace-step@v1.5-base",
  "positivePrompt": "An energetic retro synth-pop track set in a nearly empty roller rink after closing time, glowing floors, humming amplifiers, soft announcer echoes, crisp drum machines, elastic bassline, bright analog synth leads, catchy female vocals, nostalgic yet stylish, polished studio mix, strong chorus, cinematic build, playful late-night momentum",
  "negativePrompt": "muddy mix, distorted vocals, aggressive metal guitars, orchestral score, crowd noise, spoken word, lo-fi hiss, chaotic tempo changes",
  "duration": 75,
  "seed": 25165,
  "steps": 120,
  "CFGScale": 8.5,
  "settings": {
    "bpm": 112,
    "guidanceType": "apg",
    "keyScale": "A minor",
    "timeSignature": 4,
    "vocalLanguage": "en",
    "lyrics": "[Verse 1]\nWheels in circles on a painted line\nNeon streaks and a borrowed shine\nLast song spinning through the cooling air\nI keep dancing like you're still there\n\n[Pre-Chorus]\nEmpty room, electric heart\nFalling back into the start\n\n[Chorus]\nGlide with me through the afterglow\nWhere the silver speakers throb real low\nTurn the silence into a spark\nWe can make a little sun in the dark\n\n[Verse 2]\nDisco dust on a cobalt floor\nOne more lap and I want more\nMirror lights in a gentle blur\nEvery beat makes the night occur\n\n[Chorus]\nGlide with me through the afterglow\nWhere the silver speakers throb real low\nTurn the silence into a spark\nWe can make a little sun in the dark"
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "db9ad4da-7608-4fe2-9111-a9b0e6bc94a7",
  "audioUUID": "7a277cbf-5cc6-4a2a-a2b9-06b3befcc0da",
  "audioURL": "https://am.runware.ai/audio/os/a19d05/ws/5/ai/7a277cbf-5cc6-4a2a-a2b9-06b3befcc0da.mp3",
  "seed": 25165,
  "cost": 0.0058
}

Text to Audio

Glasshouse Tango Train Heist

0:00

Request

{
  "taskType": "audioInference",
  "taskUUID": "d179e09e-03aa-439a-bdc7-545ece313a41",
  "model": "runware:ace-step@v1.5-base",
  "positivePrompt": "A dramatic electro-tango heist song set aboard a luxurious cross-country train racing through frost-covered farmland at dawn. Start with nervous bandoneon, brushed snare, muted upright bass, and soft analog synth pulses, then build into a sleek groove with crisp hand percussion, staccato strings, and a confident female lead vocal. The mood is elegant, tense, witty, and fast-moving, like a jewel thief smiling during the getaway. Strong melodic hook, polished modern production, cinematic transitions, a memorable chorus, and a final section with layered harmonies and a triumphant instrumental flourish.",
  "negativePrompt": "muddy mix, distorted vocals, chaotic structure, overly aggressive rock guitars, lo-fi noise, crowd sounds, spoken word, comedy effects, childish melody, generic EDM drop",
  "duration": 118,
  "seed": 60007,
  "steps": 160,
  "CFGScale": 8.5,
  "settings": {
    "bpm": 124,
    "guidanceType": "apg",
    "keyScale": "D minor",
    "timeSignature": 4,
    "vocalLanguage": "en",
    "lyrics": "[Verse 1]\nVelvet ticket, hidden name\nSilver buckle, borrowed fame\nGlass roof shivering with the light\nI count the seconds, hold them tight\n\n[Pre-Chorus]\nKeys in my glove, sparks in my grin\nOne small breach and I slide right in\nEngines hum like a secret choir\nSteel on steel and a pulse like fire\n\n[Chorus]\nRun with the rails, don't look behind\nGold in the dawn and smoke in my mind\nKiss of danger, precise and sweet\nHeart like a drum and dust on my feet\nRun with the rails, let the whole world guess\nGrace in the theft and calm in the mess\nBy the next station I'm already gone\nLeaving my name in the break of dawn\n\n[Verse 2]\nCrystal cases, coded lock\nBlack silk timing to the ticking shock\nPorters whisper down the hall\nNo one notices at all\n\n[Pre-Chorus]\nMap in my head, flame in my chest\nEvery clean gamble demands its best\nWindows blaze with a copper sky\nI take the prize and I don't ask why\n\n[Chorus]\nRun with the rails, don't look behind\nGold in the dawn and smoke in my mind\nKiss of danger, precise and sweet\nHeart like a drum and dust on my feet\nRun with the rails, let the whole world guess\nGrace in the theft and calm in the mess\nBy the next station I'm already gone\nLeaving my name in the break of dawn\n\n[Bridge]\nIf they remember, let them remember style\nThe heel turn, the half-smile, the impossible mile\nNo shattered glass, no wasted breath\nJust a red horizon and a dance with depth\n\n[Final Chorus]\nRun with the rails, don't look behind\nGold in the dawn and smoke in my mind\nKiss of danger, precise and sweet\nHeart like a drum and dust on my feet\nRun with the rails, let the whole world guess\nGrace in the theft and calm in the mess\nBy the next station I'm already gone\nLeaving my name in the break of dawn"
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "d179e09e-03aa-439a-bdc7-545ece313a41",
  "audioUUID": "8756bdd4-4848-4d70-b735-8726996e7acd",
  "audioURL": "https://am.runware.ai/audio/os/a19d05/ws/5/ai/8756bdd4-4848-4d70-b735-8726996e7acd.mp3",
  "seed": 60007,
  "cost": 0.0122
}

Text to Audio

Brass Comet Derby Anthem

0:00

Request

{
  "taskType": "audioInference",
  "taskUUID": "bba41773-669d-4bcb-b814-c607e381a7a5",
  "model": "runware:ace-step@v1.5-base",
  "positivePrompt": "An exhilarating retro-futurist race anthem about a sky arena where brass-powered comet carts streak through painted clouds. Big band horns collide with stomping glam rock drums, wiry electric bass, sparkling synth accents, handclaps, and a charismatic lead vocal. Starts with a tense snare roll and muted trumpet motif, blooms into a massive singalong chorus, then a brief breakdown with crowd chants and whistling before a triumphant final refrain. Bright, theatrical, athletic, playful, and grand; polished studio production with memorable hooks and dynamic transitions.",
  "negativePrompt": "ambient drift, lo-fi haze, trap hi-hats, harsh distortion, death metal screaming, spoken word only, minimalist drone, chaotic structure, muddy mix, weak chorus",
  "duration": 78,
  "seed": 99684,
  "steps": 120,
  "CFGScale": 8.5,
  "settings": {
    "bpm": 146,
    "guidanceType": "apg",
    "keyScale": "D minor",
    "lyrics": "[Verse 1]\nPaint on the clouds and a spark in the wheel\nCopper-wing engines and a daredevil feel\nHelmet full of thunder, number on my sleeve\nI lean to the horizon like I never plan to leave\n\n[Pre-Chorus]\nHear the trumpets flare\nFire in the air\nEverybody counting down\n\n[Chorus]\nRun, run, comet runner, blaze across the blue\nShake the rails of heaven with the wild things that you do\nHey, hey, hold the banner, let the whole world see\nWe were born for the derby of impossible velocity\n\n[Verse 2]\nRivals at my shoulder with a grin made of chrome\nEvery turn a gamble and the storm feels like home\nKick the pedal harder, let the bright gears sing\nA hundred hearts are beating to the racket that we bring\n\n[Pre-Chorus]\nHear the trumpets flare\nFire in the air\nEverybody counting down\n\n[Chorus]\nRun, run, comet runner, blaze across the blue\nShake the rails of heaven with the wild things that you do\nHey, hey, hold the banner, let the whole world see\nWe were born for the derby of impossible velocity\n\n[Bridge]\nWhoa-oh, whistle to the rafters\nWhoa-oh, chase the afterburn\nIf we fall, we fall like meteors\nIf we win, the stars will turn\n\n[Final Chorus]\nRun, run, comet runner, blaze across the blue\nShake the rails of heaven with the wild things that you do\nHey, hey, raise the chorus, let it ring ferociously\nWe were born for the derby of impossible velocity",
    "timeSignature": 4,
    "vocalLanguage": "en"
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "bba41773-669d-4bcb-b814-c607e381a7a5",
  "audioUUID": "3329a95a-21f2-43b4-a39b-30d52f0233d0",
  "audioURL": "https://am.runware.ai/audio/os/a03d21/ws/5/ai/3329a95a-21f2-43b4-a39b-30d52f0233d0.mp3",
  "seed": 99684,
  "cost": 0.0058
}

Text to Audio

Chrome Elevator Funk Capsule

0:00

Request

{
  "taskType": "audioInference",
  "taskUUID": "644e9e2e-caa3-425a-9872-68f5047d8473",
  "model": "runware:ace-step@v1.5-base",
  "positivePrompt": "A sleek retro-futurist funk track set inside a speeding orbital elevator capsule, with elastic slap bass, crisp handclaps, talkbox-style synth leads, brushed electric piano chords, playful analog drum fills, and confident female vocals. The mood is stylish, kinetic, polished, and slightly mischievous, like a VIP commute through the stratosphere. Build from a tight grooving verse into a catchy singalong chorus, with a short instrumental break featuring synth glides and bass pops. Rich stereo production, memorable hook, clean low end, and a glossy late-70s-meets-future sound.",
  "negativePrompt": "heavy metal guitars, orchestral score, cinematic trailer booms, lo-fi tape noise, crowd chants, aggressive rap, distorted screaming, ambient drone, country twang, reggae skank, trap hi-hat rolls, glitch chaos, muddy mix",
  "duration": 78,
  "seed": 95999,
  "steps": 120,
  "CFGScale": 8.5,
  "settings": {
    "bpm": 112,
    "guidanceType": "apg",
    "keyScale": "E minor",
    "timeSignature": 4,
    "vocalLanguage": "en",
    "lyrics": "[Verse 1]\nSilver rails and velvet doors\nCity lights below like scattered cores\nMagnet shoes and mirrored shades\nWe rise above the weather grids and trade\n\n[Pre-Chorus]\nFeel the cable hum, steady and bright\nStatic on the skin, hearts in flight\n\n[Chorus]\nTake me up, up through the blue\nChrome capsule dancing with a skyline view\nNo traffic, no ground, just a glowing line\nElevator funk on borrowed time\n\n[Verse 2]\nWindow halo, midnight glare\nJetstream writing signatures in air\nPocket stars on tailored sleeves\nWe laugh where gravity forgets to breathe\n\n[Chorus]\nTake me up, up through the blue\nChrome capsule dancing with a skyline view\nNo traffic, no ground, just a glowing line\nElevator funk on borrowed time\n\n[Bridge]\nBassline leaning, motors sing\nOrbit in the making with a velvet swing\n\n[Final Chorus]\nTake me up, up through the blue\nChrome capsule dancing with a skyline view\nNo traffic, no ground, just a glowing line\nElevator funk, your hand in mine"
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "644e9e2e-caa3-425a-9872-68f5047d8473",
  "audioUUID": "c0e0e3c7-dc2b-4492-91be-033560bf9e43",
  "audioURL": "https://am.runware.ai/audio/os/a09d21/ws/5/ai/c0e0e3c7-dc2b-4492-91be-033560bf9e43.mp3",
  "seed": 95999,
  "cost": 0.0064
}